Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 13161
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory terms related to online content and copyright issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الفلك
    -0.60
     betweenstory
    -0.56
    SBATCH
    -0.56
     AssemblyTitle
    -0.55
    lamiento
    -0.54
     Performance
    -0.53
    sidemargin
    -0.53
     disambiguazione
    -0.52
    momix
    -0.52
     GetComponent
    -0.52
    POSITIVE LOGITS
     DMCA
    0.83
     copyright
    0.72
     Copyright
    0.62
     COPYRIGHT
    0.60
    Digital
    0.59
     InputDecoration
    0.59
     Digital
    0.57
     enforcement
    0.56
     digital
    0.56
     DIGITAL
    0.56
    Activations Density 0.290%

    No Known Activations